Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

TL;DR

This paper introduces a novel dual-level asymmetric mutual learning approach for unsupervised domain adaptation in person re-identification, leveraging heterogeneous networks to improve discriminative feature learning across diverse embedding spaces.

Contribution

It proposes DAML, a dual-level asymmetric mutual learning framework with heterogeneous networks that enhances knowledge transfer and discriminative feature learning in unsupervised person Re-ID.

Findings

DAML outperforms state-of-the-art methods on multiple datasets.

The approach effectively leverages asymmetric mutual learning for better domain adaptation.

Extensive experiments validate the superiority of DAML in person Re-ID tasks.

Abstract

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts.